Retrieval-Augmented Generation for Natural Language Art Provenance Searches in the Getty Provenance Index

TL;DR

This paper introduces a Retrieval-Augmented Generation framework that enhances natural language and multilingual searches in art provenance archives, improving accessibility and efficiency for researchers using the Getty Provenance Index.

Contribution

The paper presents a novel RAG-based method for semantic retrieval and summarization in art provenance research, addressing limitations of metadata-dependent search portals.

Findings

Effective retrieval and summarization of auction records

Scalable solution for navigating art market archives

Improves exploratory search capabilities

Abstract

This research presents a Retrieval-Augmented Generation (RAG) framework for art provenance studies, focusing on the Getty Provenance Index. Provenance research establishes the ownership history of artworks, which is essential for verifying authenticity, supporting restitution and legal claims, and understanding the cultural and historical context of art objects. The process is complicated by fragmented, multilingual archival data that hinders efficient retrieval. Current search portals require precise metadata, limiting exploratory searches. Our method enables natural-language and multilingual searches through semantic retrieval and contextual summarization, reducing dependence on metadata structures. We assess RAG's capability to retrieve and summarize auction records using a 10,000-record sample from the Getty Provenance Index - German Sales. The results show this approach provides a scalable solution for navigating art market archives, offering a practical tool for historians and cultural heritage professionals conducting historically sensitive research.